Guangwen Yang

reward decomposition (2) sample efficiency (2) reinforcement learning (1) benchmark evaluation (1) policy optimization (1) policy gradient (1) robust reinforcement learning (1) optimization algorithm (1) distributional reinforcement learning (1) value function (1) game playing (1) episodic memory (1) worst-case performance (1) hessian approximation (1) conjugate gradient (1) image synthesis (1) quasi-newton method (1) atari game (1) vision-language model (1) representation learning (1)